{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JVT2QVI6BLILVHW7T76VLNMEUG","short_pith_number":"pith:JVT2QVI6","schema_version":"1.0","canonical_sha256":"4d67a8551e0ad0ba9edf9ffd55b584a1a712cbc2a99a9feb63e556b495c6a4f0","source":{"kind":"arxiv","id":"1904.01578","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised training of neural mask-based beamforming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SD","authors_text":"Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach","submitted_at":"2019-04-02T12:10:23Z","abstract_excerpt":"We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood criterion derived from a spatial mixture model of the observations. It is trained from scratch without requiring any parallel data consisting of degraded input and clean training targets. Thus, training can be carried out on real recordings of noisy speech rather than simulated ones. In contrast to previous work on unsupervised training of neural mask estimators, our approach avoids the need for a possibly pre-trained tea"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.01578","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-02T12:10:23Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"103f7ba1d808c87f251aeb0a83deccb593c46b82ccbd615e60b22eef1eb7e96d","abstract_canon_sha256":"8d44455fda467e30f403503b0094d3628dea18e36a772e331ee687a3bed25587"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:08.573408Z","signature_b64":"x5YOfFkRp3H+7JZN+veT+5MhkEozaPd+epJLpZT0gg9RAJ91pG4ruy35n4tk1Wx9HNCsIc8m1jWTiE+pXUPLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d67a8551e0ad0ba9edf9ffd55b584a1a712cbc2a99a9feb63e556b495c6a4f0","last_reissued_at":"2026-05-17T23:49:08.572630Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:08.572630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised training of neural mask-based beamforming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SD","authors_text":"Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach","submitted_at":"2019-04-02T12:10:23Z","abstract_excerpt":"We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood criterion derived from a spatial mixture model of the observations. It is trained from scratch without requiring any parallel data consisting of degraded input and clean training targets. Thus, training can be carried out on real recordings of noisy speech rather than simulated ones. In contrast to previous work on unsupervised training of neural mask estimators, our approach avoids the need for a possibly pre-trained tea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01578","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.01578","created_at":"2026-05-17T23:49:08.572758+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01578v2","created_at":"2026-05-17T23:49:08.572758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01578","created_at":"2026-05-17T23:49:08.572758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG","json":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG.json","graph_json":"https://pith.science/api/pith-number/JVT2QVI6BLILVHW7T76VLNMEUG/graph.json","events_json":"https://pith.science/api/pith-number/JVT2QVI6BLILVHW7T76VLNMEUG/events.json","paper":"https://pith.science/paper/JVT2QVI6"},"agent_actions":{"view_html":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG","download_json":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG.json","view_paper":"https://pith.science/paper/JVT2QVI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01578&json=true","fetch_graph":"https://pith.science/api/pith-number/JVT2QVI6BLILVHW7T76VLNMEUG/graph.json","fetch_events":"https://pith.science/api/pith-number/JVT2QVI6BLILVHW7T76VLNMEUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG/action/storage_attestation","attest_author":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG/action/author_attestation","sign_citation":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG/action/citation_signature","submit_replication":"https://pith.science/pith/JVT2QVI6BLILVHW7T76VLNMEUG/action/replication_record"}},"created_at":"2026-05-17T23:49:08.572758+00:00","updated_at":"2026-05-17T23:49:08.572758+00:00"}